As a computer company, IBM has many different architectures contained in its products, and research in computer architecture is always very active. Over the years, IBM Research has made seminal contributions to this field. Our historical contributions in this area include the IBM S/360 model 91, which contained basic ideas for out-of-order issue high-performance processors. Pioneering work on Reduced Instruction Set Computer (RISC) architectures and compilers was done in IBM Research as part of the 801 Minicomputer project, inspired by the ideas of IBM visionary John Cocke. The Yorktown Simulation Engine was an example of a highly parallel computer for gate-level logic simulation. Other supercomputers conceived and built at IBM Research include the GF11, which made a long and massive numerical calculation to help solve a quantum chromodynamics problem, and the RP3 Parallel Processor, which was a highly parallel multiprocessor with a special switch to reduce memory contention.

Supercomputing Architecture Research

With the Blue Gene project, IBM is pushing against the ultimate technological boundaries of performance. Blue Gene is our new flagship project in supercomputing, aiming to tackle the protein-folding Grand Challenge problem with a performance of 1 petaflop (ca 10¹⁵ operations per second). More information about Blue Gene can be found on p.4.

As another example of highly parallel computing research, IBM's Deep Blue parallel computer beat the human world chess champion in 1997. Now, the parallel computing technology of Deep Blue is being applied to other areas. We recently also contributed to the ASCI White and Blue Pacific supercomputer, which are a part of the U.S. government's high-performance Accelerated Strategic Computing Initiative (ASCI).

High-Performance Microprocessor Design
We are continuing to contribute to the instruction level parallelism (ILP) and micro-architecture fields, in the context of high performance microprocessor research. The Dynamically Architected Instruction Set from Yorktown (DAISY) project aims to use binary translation to achieve 100 per cent architectural compatibility with existing processors (e. g., PowerPC, S/390®, Java™ VM) on a wide issue VLIW (Very Long Instruction Word) engine. The MET (Microarchitecture Exploration Toolset) project addresses the exploration of options in the design of PowerPC processors. The effort has led to the development and use of fast simulation tools for microarchitecture tradeoffs. The IBM VLIW research project resulted in a hardware prototype and three generations of research compilers. Our efforts in memory systems microarchitecture and timers have contributed to IBM's commercial processors, and the associated inventions have been used throughout the industry.

We are also engaged in very high frequency microprocessor design, and are aiming to construct multi-GHz processor chips in the foreseeable future. Our VLSI research is addressing both microarchitecture and circuit design challenges.

Digital Signal Processors

The world is going wireless, and digital signal processors (DSPs) are accelerating this trend. DSPs have become a ubiquitous enabler for the integration of audio, video, and communications. We are currently performing research on an ultralow power DSP/embedded processor, capable of meeting the performance requirements of the new wireless standards while consuming only a few milliwatts of power when implemented in IBM's next generation 0.13-micron CMOS technology. An important component of this research is the associated optimizing compiler being developed in conjunction with the architecture, which makes possible program development using the C language, while achieving performance comparable to assembly language without the use of custom libraries. Our unique research focus areas in DSPs include new circuit techniques for ultralow-power compiler optimizations for DSP operations, architectures and microarchitectures optimized for low-power, and system-level design experience.

Please contact Paridhi Verma to obtain copies of the Computer Science Brochure